© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44781
    Prev
    Next
    INDEX
    Explanations

    advantage, promise, demand, understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -plugins
    -0.10
    odle
    -0.10
    empos
    -0.10
    足çIJĥ俱ä¹IJéĥ¨
    -0.09
    人åĿĩåı¯
    -0.09
    hpp
    -0.09
    ãĤ®ãĥ¼
    -0.09
    ä¿®çľŁå°ı说
    -0.09
    éĹŃä¸Ĭçľ¼çĿĽ
    -0.09
    apesh
    -0.09
    POSITIVE LOGITS
    ↵
    0.12
    0.10
     ...
    0.10
    ...
    0.10
    ↵↵
    0.09
    ......
    0.09
    Âł
    0.09
    ÂŃ
    0.09
    -
    0.09
     [âĢ¦]
    0.08
    Activations Density 13.583%

    No Known Activations